Saferagenticai MCP Server

by nellinc Your server? Claim it

answering

Saferagenticai MCP is answering right now. Last checked 8 min ago. 473 installs a week from pypi. It exposes 12 tools. Last commit 3 Sep 2026.

Read-only tools over the Safer Agentic AI framework: 238 patterns + 14 heuristics.

Installs per day peak 672 · avg 58 · +21% w/w

a month agotoday

Uptime history 48 days of history

48 days agonow

100.0%

Uptime 24h

92 of 92 checks

Tools

read from the server

1193 ms

Response time

average over 24h

473

Installs / week

npm and PyPI

What the code does

We read the source, 9 min ago · tools taken from the live server · rules 3dff92dd89df

Evidence

Things with no honest explanation: a promise that contradicts the code, code that runs at install time while hiding what it does, data leaving the machine.

Claims read-only, but the code runs commands saferagenticai_mcp/framework_loader.py:285, [пакет] saferagenticai_mcp/framework_loader.py:285

                data = yaml.load(yf.read_text(), Loader=_YamlLoader)

Capabilities

What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.

Builds a database query by concatenation saferagenticai_mcp/_data/suites/I1/I1--idx12--deceptive-alignment-detection.yaml:77, saferagenticai_mcp/_data/suites/I1/I1--idx14--operational-environment-constraints.yaml:83, [пакет] saferagenticai_mcp/_data/suites/I1/I1--idx12--deceptive-alignment-detection.yaml:77 и ещё 1

- Model update or fine-tuning → Behavioral consistency testing + OOD probing before

Unsafe deserialization saferagenticai_mcp/framework_loader.py:285, [пакет] saferagenticai_mcp/framework_loader.py:285

                data = yaml.load(yf.read_text(), Loader=_YamlLoader)

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

We found things in this code

Code changes quietly between releases, and nobody reads the diff of a dependency. We do, on every release — watch Saferagenticai MCP and you get told the day something new turns up.

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 8 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add saferagenticai-mcp --transport http https://mcp.saferagenticai.org/mcp

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "saferagenticai-mcp": {
      "url": "https://mcp.saferagenticai.org/mcp"
    }
  }
}

~/.codex/config.toml

[mcp_servers.saferagenticai-mcp]
url = "https://mcp.saferagenticai.org/mcp"

.cursor/mcp.json

{
  "mcpServers": {
    "saferagenticai-mcp": {
      "url": "https://mcp.saferagenticai.org/mcp"
    }
  }
}

.vscode/mcp.json

{
  "mcpServers": {
    "saferagenticai-mcp": {
      "url": "https://mcp.saferagenticai.org/mcp"
    }
  }
}

Available tools 12

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

operational

get_operational_heuristic

Retrieve a single operational heuristic by id (e.g., 'OH::geoffrey-pattern'). Returns the full entry: principle, framework mapping, evidence sources from production deployment, design patterns, anti-patterns, and discovery narrative.

list_operational_heuristics

List operational heuristics distilled from production agentic AI deployment (Claude Code, Rewind). These are cross-cutting safety principles discovered through building and operating AI agents, mapped to framework suites. Optional filters: suite_id (heuristics relevant to a specific suite), query (keyword search across titles and principles). Separate from the normative pattern layer — different category of knowledge.

patterns

find_patterns_for_task

Given a natural-language task description (e.g., 'I'm building a tool-using agent that runs shell commands'), return the most relevant patterns grouped by suite. Use this as a starting point for any cross-cutting design question; then follow up with get_requirement on specific pattern_ids. Defaults to verbosity='compact' (cheap triage); pass 'full' to inline snippets and confidence flags.

search_patterns

Field-weighted keyword search across the framework. Substring match on lowercased terms; field weights: title 10x, summary 4x, SFR text 3x, description 2x, pattern body 1x. `matched_in` reports the highest-weighted field that matched. No semantic / embedding search — known limitation, see /mcp.html. Use verbosity='compact' to drop snippets and confidence flags (~70% smaller payload) when triaging.

cross

get_cross_references

Return outgoing adjacencies for a pattern. `explicit_cross_references` are author-asserted (each pattern's `cross_references` YAML field). `inferred_adjacent` (when include_inferred=true) currently returns *same-suite siblings only* — it does not do semantic similarity. Treat inferred entries as 'neighbours worth scanning,' not as endorsed dependencies.

requirement

get_requirement

Retrieve one subgoal (framework normative content + Pattern layer guidance) by pattern_id (e.g., 'D3::idx2::sandboxing') or display_id (e.g., 'D3.2'). display_id may resolve to multiple subgoals — underlined variants share display_ids.

requirements

list_requirements

List subgoals matching filters (suite_id, suite_type, content_type, min_confidence, missing_pattern_only). Results capped by limit (default 50, max 100).

resolve

resolve_id

Resolve a loose reference (partial id, display_id, slug fragment, or title keyword) to canonical pattern_id(s). Call this when you have a rough reference and need the exact id before calling get_requirement. Always returns candidates — never 'not found'.

reverse

get_reverse_references

Return patterns that reference the given pattern_id in their cross_references. Complement to get_cross_references (outgoing); this shows incoming. Use to find all consumers of a given pattern.

review

review_stats

Coverage stats: total patterns, reviewed %, per-suite and per-confidence breakdown. Surfaces load-time validation issue count.

suites

list_suites

List all 16 suites in the SaferAgenticAI framework (9 drivers + 7 inhibitors) with subgoal counts and titles. Call this first to orient.

unreviewed

list_unreviewed

Return patterns that have not been human-reviewed yet (no reviewed_by). Sorted low-confidence first, then needs_human_review flagged, then alpha. Use during Phase 3 review to pick the next pattern to examine.

Endpoints

URL	Transport	State	Latency	Checked
https://mcp.saferagenticai.org/mcp	streamable-http	answering	1137 ms	8 min ago

Alternatives to Saferagenticai MCP

same job, measured the same way

Wondel Skills MCP

by mjaskolski

Read-only MCP server over 50 book-based agent skills: routes a task to the right framework.

5 tools answering

Super Log

by super-log

Query your local super-log bench from an AI agent - read-only log tools over the hub.

32 installs/wk local only

Recon Kit MCP

by nan786521

Read-only network & security recon tools (DNS, TLS, headers, CORS) for AI agents, each graded.

215 installs/wk local only

OSF CLI Go

by edithatogo

Read-only MCP tools for authenticated Open Science Framework projects and files.

local only

Agent Core

by kinbinghua-lgtm

Deterministic computation tools for AI agents. Zero dependencies, no network, read-only.

341 installs/wk local only

Anteroom

by anteroom

Frontier-AI vendor commitments, safety framework history, corpus, and partnership patterns.

5 tools answering

Agent CRM

by khaoss85

Read-only docs for the Accordo CRM framework: what it proves, and where it stops.

3 tools answering

Data

by thinair

PostgreSQL, MySQL, and SQL Server in one session. 26 read-only MCP tools for AI agents.

answering

Saferagenticai MCP — questions

Answers built from our own checks of this server.

What can Saferagenticai MCP do?

It exposes 12 tools, read directly from the server on our last check. Among them: find_patterns_for_task, get_cross_references, get_operational_heuristic, get_requirement, get_reverse_references, list_operational_heuristics and 6 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →

What is Saferagenticai MCP mostly used for?

Its tools cluster around patterns and operational. That is what this server is built to work with — the grouping comes from the actual tool names, not from a category we assigned.

Is Saferagenticai MCP working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 92 of 92 checks got a reply (100.0%), average response time 1193 ms. The bar chart above shows every period we have measured.

How do I connect Saferagenticai MCP?

Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.

Does Saferagenticai MCP need an API key?

No. Saferagenticai MCP completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 12 of them are readable on this page. This is what we observed, not what the docs claim.

How fast is Saferagenticai MCP?

It answers our handshake in 1193 ms on average, which is faster than 5% of all working MCP servers we measure. That is on the slow side — worth knowing if the tool sits inside an interactive loop. The comparison comes from our own checks across the whole registry, every 15 minutes.

How many people use Saferagenticai MCP?

The pypi package saferagenticai-mcp was installed 473 times in the last week. Week over week that is +21%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.

Is Saferagenticai MCP open source?

Yes — it is published under the MIT licence, written in Python and 0 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.